Giter Site home page Giter Site logo

schn's Introduction

Discriminative Visual Similarity Search with Semantically Cycle-consistent Hashing Networks

Here is the official codebase for Discriminative Visual Similarity Search with Semantically Cycle-consistent Hashing Networks. MMAsia2022 Version
Extended TOMM Version
This repo contains two versions of SCHN(the original SCHN on MMAsia2022 and the one with the discriminator TOMM). You can specify the variant by the method_name constant in run.py(Line 18).

REQUIREMENTS

requirements.txt contains libraries used in my environments. Though other versions may also work, I have no time to test and can't guarantee any of that.

DATASETS

  1. CIFAR-10

  2. NUS-WIDE Password: uhr3

  3. MIR-Flickr 25K version

Project Structure

The structure of the project files should go as follows.

.
├── data
│   ├── cifar10.py
│   ├── data_loader.py
│   ├── flickr25k.py
│   ├── imagenet.py
│   ├── __init__.py
│   ├── nus_wide.py
│   └── transform.py
├── dataset
│   ├── cifar-10-batches-py
│   │   ├── batches.meta
│   │   ├── data_batch_1
│   │   ├── data_batch_2
│   │   ├── data_batch_3
│   │   ├── data_batch_4
│   │   ├── data_batch_5
│   │   ├── readme.html
│   │   └── test_batch
│   ├── Flickr
│   │   ├── database_label.txt
│   │   ├── db_image.txt
│   │   ├── mirflickr
│   │   │   ├── im21110.jpg
│   │   │   └── ......
│   │   ├── test_image_m.txt
│   │   └── test_label.txt
│   └── NUS-WIDE
│       ├── database_img.txt
│       ├── database_label_onehot.txt
│       ├── database_label.txt
│       ├── images
│       │   ├── 0068_2569963337.jpg
│       │   └── ......
│       ├── img_tc10.txt
│       ├── README.md
│       ├── targets_onehot_tc10.txt
│       ├── targets_tc10.txt
│       ├── test_img.txt
│       ├── test_label_onehot.txt
│       ├── test_label.txt
│       └── t.txt
├── logs
├── main_mmasia.py
├── main_tomm.py
├── modules
│   ├── alexnet.py
│   ├── all_in_one.py
│   ├── gcn
│   │   ├── layers.py
│   │   ├── models.py
│   │   └── __pycache__
│   │       ├── layers.cpython-39.pyc
│   │       └── models.cpython-39.pyc
│   ├── __init__.py
│   └── mlp.py
├── README.md
├── requirements.txt
├── run.py
└── utils
    ├── evaluate.py
    └── __init__.py

schn's People

Contributors

jalinwang avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.